TTIC’s Submission to WMT-SLT 23

Marcelo Sandoval-Castaneda, Yanhong Li, Bowen Shi, Diane Brentari, Karen Livescu, Gregory Shakhnarovich


Abstract
In this paper, we describe TTIC’s submission to WMT 2023 Sign Language Translation task on the Swiss-German Sign Language (DSGS) to German track. Our approach explores the advantages of using large-scale self-supervised pre-training in the task of sign language translation, over more traditional approaches that rely heavily on supervision, along with costly labels such as gloss annotations. The proposed model consists of a VideoSwin transformer for image encoding, and a T5 model adapted to receive VideoSwin features as input instead of text. In WMT-SLT 22’s development set, this system achieves 2.03 BLEU score, a 59% increase over the previous best reported performance. In the official test set, our primary submission achieves 1.1 BLEU score and 17.0 chrF score.
Anthology ID:
2023.wmt-1.35
Volume:
Proceedings of the Eighth Conference on Machine Translation
Month:
December
Year:
2023
Address:
Singapore
Editors:
Philipp Koehn, Barry Haddow, Tom Kocmi, Christof Monz
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
344–350
Language:
URL:
https://aclanthology.org/2023.wmt-1.35
DOI:
10.18653/v1/2023.wmt-1.35
Bibkey:
Cite (ACL):
Marcelo Sandoval-Castaneda, Yanhong Li, Bowen Shi, Diane Brentari, Karen Livescu, and Gregory Shakhnarovich. 2023. TTIC’s Submission to WMT-SLT 23. In Proceedings of the Eighth Conference on Machine Translation, pages 344–350, Singapore. Association for Computational Linguistics.
Cite (Informal):
TTIC’s Submission to WMT-SLT 23 (Sandoval-Castaneda et al., WMT 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.wmt-1.35.pdf